© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105963
    Prev
    Next
    INDEX
    Explanations

    marketing industry

    np_acts-logits-general · gemini-2.5-flash-lite

    analyze linux commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leo
    0.57
    ა
    0.56
     Dois
    0.56
    獎
    0.55
    瑀
    0.54
    人物
    0.54
    राइट
    0.52
    棣
    0.52
    Deux
    0.52
    物語
    0.51
    POSITIVE LOGITS
     perturbed
    0.46
     الند
    0.42
    ousing
    0.42
     краю
    0.42
     ван
    0.41
     phases
    0.40
    leading
    0.40
    рование
    0.40
    perturbed
    0.39
    phases
    0.39
    Activations Density 0.000%

    No Known Activations